diff --git a/README.md b/README.md index 0b9e9fd..f201a75 100644 --- a/README.md +++ b/README.md @@ -9,8 +9,7 @@ A curated list of awesome Indoor Scene Synthesis papers. ## Papers -
-3D Scene synthesis +### 3D Scene synthesis
Compositional Mesh Generation @@ -46,45 +45,70 @@ A curated list of awesome Indoor Scene Synthesis papers. - [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://arxiv.org/abs/1811.12463) | CVPR 2019 - [Scene Synthesis via Uncertainty-Driven Attribute Synchronization](https://arxiv.org/abs/2108.13499) | ICCV 2021 | [github](https://github.com/brownvc/fast-synth) - [RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation](https://arxiv.org/abs/2310.10027), Zhao et al., 3DV 2024 | [github](https://github.com/zhao-yiqun/RoomDesigner) | [bibtext](./citations/roomdesigner.txt) +
-- -- Model training with scene graph +
+Model Training with Scene Graph + - [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://arxiv.org/abs/2402.04717) | ICLR 2024 | [github](https://github.com/chenguolin/InstructScene) | [project](https://chenguolin.github.io/projects/InstructScene/) - [CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion](https://arxiv.org/abs/2305.16283) | NIPS 2023 | [github](https://github.com/ymxlzgy/commonscenes) | [project](https://sites.google.com/view/commonscenes) - [3D Scene Diffusion Guidance using Scene Graphs](https://arxiv.org/abs/2308.04468) | arXiv 2023 - [SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation](https://arxiv.org/abs/1907.11308) | ICCV 2019 +
- -- using 2D prior +
+Using 2D Prior + - [Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors](https://arxiv.org/abs/2406.00687) | [project](https://lay-a-scene.github.io/) +
+
+Procedure / Human Design Rules -- procedure / human design rules - [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://arxiv.org/abs/2406.11824) | [github](https://github.com/princeton-vl/infinigen) | [project](https://infinigen.org/) - [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://arxiv.org/abs/2312.09067) | [github](https://github.com/allenai/Holodeck) | [project](https://yueyang1996.github.io/holodeck/) - [I-Design: Personalized LLM Interior Designer](https://arxiv.org/abs/2404.02838), arxiv 2024 | [github](https://github.com/atcelen/IDesign/?tab=readme-ov-file) | [project](https://atcelen.github.io/I-Design/) - [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://procthor.allenai.org/), Deitke et al., NeurIPS 2022 | [github](https://github.com/allenai/procthor) | [bibtex](./citations/procthor.txt)
- -- MCMC -- [Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars](https://arxiv.org/abs/1704.00112) | IJCV (2018) + +
+Conditioned on Human Montion + +- [Scene Synthesis from Human Motion](https://arxiv.org/abs/2301.01424) | SIGGRAPH Asia 2022 | [github](https://github.com/onestarYX/summon) | [project](https://lijiaman.github.io/projects/summon/) +- [Pose2Room: Understanding 3D Scenes from Human Activities](https://arxiv.org/abs/2112.03030) | ECCV 2022 | [github](https://arxiv.org/abs/2112.03030) | [project](https://yinyunie.github.io/pose2room-page/) +- [Human-centric Indoor Scene Synthesis Using Stochastic Grammar](https://arxiv.org/abs/1808.08473v1) | CVPR 2018 +- [Rearrange Indoor Scenes for Human-Robot Co-Activity](https://arxiv.org/abs/2303.05676) | ICRA 2023 | [github](https://github.com/Rayckey/scene_coactivity) | [project](https://sites.google.com/view/coactivity) +- [MIME: Human-Aware 3D Scene Generation](https://arxiv.org/abs/2212.04360) | CVPR 2023 | [github](https://github.com/yhw-yhw/MIME) | [project](https://mime.is.tue.mpg.de/) +- [Language-driven Scene Synthesis using Multi-conditional Diffusion Model](https://arxiv.org/abs/2310.15948) | arXiv 2023 | [github](https://github.com/andvg3/LSDM) | [project](https://lang-scene-synth.github.io/)
+
-Scene Texture +Condition on 2D Image -- [Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details](https://arxiv.org/abs/2308.16880) | CVPR 2023 +- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://arxiv.org/abs/2002.12212) | CVPR 2020 | [github](https://github.com/GAP-LAB-CUHK-SZ/Total3DUnderstanding) | [project](https://yinyunie.github.io/Total3D/) +- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://arxiv.org/pdf/2103.06422) | CVPR 2021 | [github](https://github.com/chengzhag/Implicit3DUnderstanding) |[project](https://chengzhag.github.io/publication/im3d/)
+
-2D Layout / General layout +MCMC -- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://arxiv.org/abs/2006.14615) | ICCV2021 | [github](https://github.com/kampta/DeepLayout) | [project](https://kampta.github.io/layout/) +- [Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars](https://arxiv.org/abs/1704.00112) | IJCV (2018)
+### Scene Texture + +- [Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details](https://arxiv.org/abs/2308.16880) | CVPR 2023 + + +### 2D Layout / General layout + +- [LayoutTransformer: Layout Generation and Completion with Self-attention](https://arxiv.org/abs/2006.14615) | ICCV2021 | [github](https://github.com/kampta/DeepLayout) | [project](https://kampta.github.io/layout/) +
Scene @@ -102,26 +126,6 @@ A curated list of awesome Indoor Scene Synthesis papers.
-
-conditioned on Human Montion - -- [Scene Synthesis from Human Motion](https://arxiv.org/abs/2301.01424) | SIGGRAPH Asia 2022 | [github](https://github.com/onestarYX/summon) | [project](https://lijiaman.github.io/projects/summon/) -- [Pose2Room: Understanding 3D Scenes from Human Activities](https://arxiv.org/abs/2112.03030) | ECCV 2022 | [github](https://arxiv.org/abs/2112.03030) | [project](https://yinyunie.github.io/pose2room-page/) -- [Human-centric Indoor Scene Synthesis Using Stochastic Grammar](https://arxiv.org/abs/1808.08473v1) | CVPR 2018 -- [Rearrange Indoor Scenes for Human-Robot Co-Activity](https://arxiv.org/abs/2303.05676) | ICRA 2023 | [github](https://github.com/Rayckey/scene_coactivity) | [project](https://sites.google.com/view/coactivity) -- [MIME: Human-Aware 3D Scene Generation](https://arxiv.org/abs/2212.04360) | CVPR 2023 | [github](https://github.com/yhw-yhw/MIME) | [project](https://mime.is.tue.mpg.de/) -- [Language-driven Scene Synthesis using Multi-conditional Diffusion Model](https://arxiv.org/abs/2310.15948) | arXiv 2023 | [github](https://github.com/andvg3/LSDM) | [project](https://lang-scene-synth.github.io/) -
- - -
-Condition on 2D Image - -- [Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image](https://arxiv.org/abs/2002.12212) | CVPR 2020 | [github](https://github.com/GAP-LAB-CUHK-SZ/Total3DUnderstanding) | [project](https://yinyunie.github.io/Total3D/) -- [Holistic 3D Scene Understanding from a Single Image with Implicit Representation](https://arxiv.org/pdf/2103.06422) | CVPR 2021 | [github](https://github.com/chengzhag/Implicit3DUnderstanding) |[project](https://chengzhag.github.io/publication/im3d/) -
- - ## Datasets